A review of information sources and analysis methods for data driven decision aids in child and adolescent mental health services.

OBJECTIVE: Clinical data analysis relies on effective methods and appropriate data. Recognizing distinctive clinical services and service functions may lead to improved decision-making. Our first objective is to categorize analytical methods, data sources, and algorithms used in current research on information analysis and decision support in child and adolescent mental health services (CAMHS). Our secondary objective is to identify the potential for data analysis in different clinical services and functions in which data-driven decision aids can be useful. MATERIALS AND METHODS: We searched related studies in Science Direct and PubMed from 2018 to 2023(Jun), and also in ACM (Association for Computing Machinery) Digital Library, DBLP (Database systems and Logic Programming), and Google Scholar from 2018 to 2021. We have reviewed 39 studies and extracted types of analytical methods, information content, and information sources for decision-making. RESULTS: In order to compare studies, we developed a framework for characterizing health services, functions, and data features. Most data sets in reviewed studies were small, with a median of 1,550 patients and 46,503 record entries. Structured data was used for all studies except two that used textual clinical notes. Most studies used supervised classification and regression. Service and situation-specific data analysis dominated among the studies, only two studies used temporal, or process features from the patient data. This paper presents and summarizes the utility, but not quality, of the studies according to the care situations and care providers to identify service functions where data-driven decision aids may be relevant. CONCLUSIONS: Frameworks identifying services, functions, and care processes are necessary for characterizing and comparing electronic health record (EHR) data analysis studies. The majority of studies use features related to diagnosis and assessment and correspondingly have utility for intervention planning and follow-up. Profiling the disease severity of referred patients is also an important application area.

Pharmacokinetic correlates of clinical response in a naturalistic sample of escitalopram-treated patients.

OBJECTIVE: We assessed pharmacokinetic correlates of treatment response to escitalopram using a large therapeutic drug monitoring database. METHODS: A large naturalistic sample of patients receiving escitalopram was analyzed. Responders were defined as 'very much improved' or 'much improved' based on the Clinical Global Impression - Improvement score, CGI-I. We compared responders (n = 83) vs. non-responders (n = 388) with the primary outcome being the escitalopram plasma concentration and concentration corrected by the daily dose (C/D ratio). Effects of age, sex, body-mass-index (BMI), and C/D ratio were assessed in a multivariate logistic regression model predicting response. RESULTS: There were no statistically significant differences in clinical and demographic characteristics between responders vs. non-responders. There were also no differences between escitalopram daily doses or plasma concentrations, while C/D ratios were significantly higher in non-responders than in responders (1.6 ± 1.7 vs. 1.2 ± 0.9 (ng/mL)/(mg/day), p = 0.007); C/D ratios (odds ratio 0.52, 95% confidence interval 0.34-0.80, p < 0.003) were associated with response to escitalopram, after controlling for age, sex, and BMI. CONCLUSIONS: Patients with low clearance of escitalopram as reflected upon high C/D ratios may be less likely respond to escitalopram. Identifying these patients during dose titration may support clinical decision-making, including switching to a different antidepressant instead of increasing daily dose.

Time-sensitive changes in the maternal brain and their influence on mother-child attachment.

Pregnancy and the postpartum period are characterized by an increased neuroplasticity in the maternal brain. To explore the dynamics of postpartum changes in gray matter volume (GMV), magnetic resonance imaging was performed on 20 healthy postpartum women immediately after childbirth and at 3-week intervals for 12 postpartum weeks. The control group comprised 20 age-matched nulliparous women. The first 6 postpartum weeks (constituting the subacute postpartum period) are associated with decreasing progesterone levels and a massive restructuring in GMV, affecting the amygdala/hippocampus, the prefrontal/subgenual cortex, and the insula, which approach their sizes in nulliparous women only around weeks 3-6 postpartum. Based on the amygdala volume shortly after delivery, the maternal brain can be reliably distinguished from the nulliparous brain. Even 12 weeks after childbirth, the GMV in the dorsomedial prefrontal cortex, and the cortical thickness of the subgenual and lateral prefrontal cortices do not reach the pre-pregnancy levels. During this period, a volume decrease is seen in the cerebellum, the thalamus, and the dorsal striatum. A less hostile behavior toward the child at 6-12 weeks postpartum is predicted by the GMV change in the amygdala, the temporal pole, the olfactory gyrus, the anterior cingulate, the thalamus and the cerebellum in the same period. In summary, the restructuring of the maternal brain follows time-dependent trajectories. The fact that the volume changes persist at 12 weeks postpartum indicates that the maternal brain does not fully revert to pre-pregnancy physiology. Postpartum neuroplasticity suggests that these changes may be particularly significant in the regions important for parenting.

Challenges in Interpreting Norwegian Child and Adolescent Mental Health Records.

The Electronic Health Record system BUPdata served Norwegian Child and Adolescent Mental Health Services (CAMHS) for over 35 years and is still an important source of information for understanding clinical practice. Secondary usage of clinical data enables learning and service quality improvement. We present some insights from explorative data analysis for interpreting the records of patients referred for hyperkinetic disorders. The major challenges were data preparation, pre-analysis, imputation, and validation. We summarize the main characteristics, spot anomalies, and detect errors. The results include observations about the patient referral diversity based on 12 different variables. We modeled the activities in an individual episode of care, described our clinical observations among data, and discussed the challenges of data analysis.

Longitudinal hippocampal subfield development associated with psychotic experiences in young people.

Hippocampal volumetric reductions are observed across the psychosis spectrum, with interest in the localisation of these reductions within the hippocampal subfields increasing. Deficits of the CA1 subfield in particular have been implicated in the neuropathophysiology of psychotic disorders. Investigating the trajectory of these abnormalities in healthy adolescents reporting sub-threshold psychotic experiences (PE) can provide insight into the neural mechanisms underlying psychotic symptoms without the potentially confounding effects of a formal disorder, or antipsychotic medication. In this novel investigation, a sample of 211 young people aged 11-13 participated initially in the Adolescent Brain Development study. PE classification was determined by expert consensus at each timepoint. Participants underwent neuroimaging at 3 timepoints, over 6 years. 78 participants with at least one scan were included in the final sample; 33 who met criteria for a definite PE at least once across all the timepoints (PE group), and 45 controls. Data from bilateral subfields of interest (CA1, CA2/3, CA4/DG, presubiculum and subiculum) were extracted for Linear Mixed Effects analyses. Before correction, subfield volumes were found to increase in the control group and decrease in the PE group for the right CA2 and CA2/3 subfields, with moderate to large effect sizes (d = -0.61, and d = -0.79, respectively). Before correction, right subiculum and left presubiculum volumes were reduced in the PE group compared to controls, regardless of time, with moderate effect sizes (d = -0.52, and d = -0.59, respectively). However, none of these effects survived correction. Severity of symptoms were not associated with any of the noted subfields. These findings provide novel insight to the discussion of the role of hippocampal subfield abnormalities in the pathophysiology underlying psychotic experiences.

Specific alterations of resting-state functional connectivity in the triple network related to comorbid anxiety in major depressive disorder.

The brain's default mode network (DMN) and the executive control network (ECN) switch engagement are influenced by the ventral attention network (VAN). Alterations in resting-state functional connectivity (RSFC) within this so-called triple network have been demonstrated in patients with major depressive disorder (MDD) or anxiety disorders (ADs). This study investigated alterations in the RSFC in patients with comorbid MDD and ADs to better understand the pathophysiology of this prevalent group of patients. Sixty-eight participants (52.9% male, mean age 35.3 years), consisting of 25 patients with comorbid MDD and ADs (MDD + AD), 20 patients with MDD only (MDD) and 23 healthy controls (HCs) were investigated clinically and with 3T resting-state fMRI. RSFC utilizing a seed-based approach within the three networks belonging to the triple network was compared between the groups. Compared with HC, MDD + AD showed significantly reduced RSFC between the ECN and the VAN, the DMN and the VAN and within the ECN. No differences could be found for the MDD group compared with both other groups. Furthermore, symptom severity and medication status did not affect RSFC values. The results of this study show a distinct set of alterations of RSFC for patients with comorbid MDD and AD compared with HCs. This set of dysfunctions might be related to less adequate switching between the DMN and the ECN as well as poorer functioning of the ECN. This might contribute to additional difficulties in engaging and utilizing consciously controlled emotional regulation strategies.

Transdiagnostic inflexible learning dynamics explain deficits in depression and schizophrenia.

Deficits in reward learning are core symptoms across many mental disorders. Recent work suggests that such learning impairments arise by a diminished ability to use reward history to guide behaviour, but the neuro-computational mechanisms through which these impairments emerge remain unclear. Moreover, limited work has taken a transdiagnostic approach to investigate whether the psychological and neural mechanisms that give rise to learning deficits are shared across forms of psychopathology. To provide insight into this issue, we explored probabilistic reward learning in patients diagnosed with major depressive disorder (n = 33) or schizophrenia (n = 24) and 33 matched healthy controls by combining computational modelling and single-trial EEG regression. In our task, participants had to integrate the reward history of a stimulus to decide whether it is worthwhile to gamble on it. Adaptive learning in this task is achieved through dynamic learning rates that are maximal on the first encounters with a given stimulus and decay with increasing stimulus repetitions. Hence, over the course of learning, choice preferences would ideally stabilize and be less susceptible to misleading information. We show evidence of reduced learning dynamics, whereby both patient groups demonstrated hypersensitive learning (i.e. less decaying learning rates), rendering their choices more susceptible to misleading feedback. Moreover, there was a schizophrenia-specific approach bias and a depression-specific heightened sensitivity to disconfirmational feedback (factual losses and counterfactual wins). The inflexible learning in both patient groups was accompanied by altered neural processing, including no tracking of expected values in either patient group. Taken together, our results thus provide evidence that reduced trial-by-trial learning dynamics reflect a convergent deficit across depression and schizophrenia. Moreover, we identified disorder distinct learning deficits.

Treatment of adult attention-deficit hyperactivity disorder (ADHD) with transcranial direct current stimulation (tDCS): study protocol for a parallel, randomized, double-blinded, sham-controlled, multicenter trial (Stim-ADHD).

Transcranial direct current stimulation (tDCS) is a non-invasive brain stimulation treatment used as an alternative or complementary treatment for various neuropsychiatric disorders, and could be an alternative or add-on therapy to psychostimulants in attention-deficit hyperactivity disorder (ADHD). Previous studies provided some evidence for improvements in cognition and clinical symptoms in pediatric and adult ADHD patients. However, data from multi-center randomized controlled trials (RCTs) for this condition are lacking. Thus, our aim is to evaluate short- and mid-term effects of tDCS in this multi-center, randomized, double blind, and sham-controlled, parallel group clinical trial with a 1:1 randomization ratio. Primary endpoint is the total score of DSM-IV scale of the internationally established Conners' Adult ADHD Rating Scales (German self-report screening version, CAARS-S-SR), at day 14 post-intervention (p.i.) to detect short-term lasting effects analyzed via analyses of covariance (ANCOVAs). In case of significant between-groups differences at day 14 p.i., hierarchically ordered hypotheses on mid-term lasting effects will be investigated by linear mixed models with visit (5 time points), treatment, treatment by visit interaction, and covariates as fixed categorical effects plus a patient-specific visit random effect, using an unstructured covariance structure to model the residual within-patient errors. Positive results of this clinical trial will expand the treatment options for adult ADHD patients with tDCS and provide an alternative or add-on therapy to psychostimulants with a low risk for side effects.Trial Registration The trial was registered on July 29, 2022 in the German Clinical Trials Register (DRKS00028148).

Neuroanatomical correlates of aggressiveness: a case-control voxel- and surface-based morphometric study.

Aggression occurs across the population ranging on a symptom continuum. Most previous studies have used magnetic resonance imaging in clinical/forensic samples, which is associated with several confounding factors. The present study examined structural brain characteristics in two healthy samples differing only in their propensity for aggressive behavior. Voxel- and surface-based morphometry (SBM) analyses were performed on 29 male martial artists and 32 age-matched male controls. Martial artists had significantly increased mean gray matter volume in two frontal (left superior frontal gyrus and bilateral anterior cingulate cortex) and one parietal (bilateral posterior cingulate gyrus and precuneus) brain clusters compared to controls (whole brain: p < 0.001, cluster level: family-wise error (FWE)-corrected). SBM analyses revealed a trend for greater gyrification indices in martial artists compared to controls in the left lateral orbital frontal cortex and the left pars orbitalis (whole brain: p < 0.001, cluster level: FWE-corrected). The results indicate brain structural differences between martial artists and controls in frontal and parietal brain areas critical for emotion processing/inhibition of emotions as well as empathic processes. The present study highlights the importance of studying healthy subjects with a propensity for aggressive behavior in future structural MRI research on aggression.

Normative Modeling of Brain Morphometry Across the Lifespan Using CentileBrain: Algorithm Benchmarking and Model Optimization.

We present an empirically benchmarked framework for sex-specific normative modeling of brain morphometry that can inform about the biological and behavioral significance of deviations from typical age-related neuroanatomical changes and support future study designs. This framework was developed using regional morphometric data from 37,407 healthy individuals (53% female; aged 3-90 years) following a comparative evaluation of eight algorithms and multiple covariate combinations pertaining to image acquisition and quality, parcellation software versions, global neuroimaging measures, and longitudinal stability. The Multivariate Factorial Polynomial Regression (MFPR) emerged as the preferred algorithm optimized using nonlinear polynomials for age and linear effects of global measures as covariates. The MFPR models showed excellent accuracy across the lifespan and within distinct age-bins, and longitudinal stability over a 2-year period. The performance of all MFPR models plateaued at sample sizes exceeding 3,000 study participants. The model and scripts described here are freely available through CentileBrain (https://centilebrain.org/).

Baby blues, premenstrual syndrome and postpartum affective disorders: intersection of risk factors and reciprocal influences.

BACKGROUND: The aetiology and consequences of 'baby blues' (lower mood following childbirth) are yet to be sufficiently investigated with respect to an individual's clinical history. AIMS: The primary aim of the study was to assess the symptoms of baby blues and the relevant risk factors, their associations with clinical history and premenstrual syndrome (PMS), and their possible contribution to the early recognition of postpartum depression (PPD). METHOD: Beginning shortly after childbirth, 369 mothers were followed up for 12 weeks. Information related to their clinical history, PMS, depression, stress and mother-child attachment was collected. At 12 weeks, mothers were classified as non-depressed, or with either PPD or adjustment disorder. RESULTS: A correlation was found between the severity of baby blues and PMS (r = 0.397, P < 0.001), with both conditions increasing the possibility of adjustment disorder and PPD (baby blues: OR = 6.72, 95% CI 3.69-12.25; PMS: OR = 3.29, 95% CI 2.01-5.39). Baby blues and PMS independently predicted whether a mother would develop adjustment disorder or PPD after childbirth (χ2(64) = 198.16, P < 0.001). Among the non-depressed participants, baby blues were found to be associated with primiparity (P = 0.012), family psychiatric history (P = 0.001), PMS (P < 0.001) and childhood trauma (P = 0.017). CONCLUSIONS: Baby blues are linked to a number of risk factors and a history of PMS, with both conditions adding to the risk of PPD. The neuroendocrine effects on mood need be understood in the context of individual risk factors. The assessment of both baby blues and PMS symptoms within the first postpartum days may contribute to an early identification of PPD.

Prevalence of COVID-19 and Psychotropic Drug Treatment in Psychiatric In-patients in Germany in 2020: Results from a Nationwide Pilot Survey.

INTRODUCTION: In patients with a pre-existing mental disorder, an increased risk for a first manifestation of a psychiatric disorder in COVID-19 patients, a more severe course of COVID-19 and an increased mortality have been described. Conversely, observations of lower COVID-19 incidences in psychiatric in-patients suggested protective effects of psychiatric treatment and/or psychotropic drugs against COVID-19. METHODS: A retrospective multi-center study was conducted in 24 German psychiatric university hospitals. Between April and December 2020 (the first and partly second wave of COVID-19), the effects of COVID-19 were assessed on psychiatric in-patient care, the incidence and course of a SARS-CoV-2 infection, and treatment with psychotropic drugs. RESULTS: Patients (n=36,322) were admitted to the hospitals. Mandatory SARS-CoV-2 tests before/during admission were reported by 23 hospitals (95.8%), while 18 (75%) conducted regular testing during the hospital stay. Two hundred thirty-two (0.6%) patients were tested SARS-CoV-2-positive. Thirty-seven (16%) patients were receiving medical treatment for COVID-19 at the psychiatric hospital, ten (4.3%) were transferred to an intermediate/intensive care unit, and three (1.3%) died. The most common prescription for SARS-CoV-2-positive patients was for second-generation antipsychotics (n=79, 28.2%) and antidepressants (SSRIs (n=38, 13.5%), mirtazapine (n=36, 12.9%) and SNRIs (n=29, 10.4%)). DISCUSSION: Contrary to previous studies, our results showed a low number of infections and mortality in SARS-CoV-2-positive psychiatric patients. Several preventive measures seem effective to protect this vulnerable group. Our observations are compatible with the hypothesis of a protective effect of psychotropic drugs against COVID-19 as the overall mortality and need for specific medical treatment was low.

Dynamic Stability of Volatile Organic Compounds in Respiratory Air in Schizophrenic Patients and Its Potential Predicting Efficacy of TAAR Agonists.

OBJECTIVES: Volatile organic compounds (VOCs) in the breathing air were found to be altered in schizophrenia patients compared to healthy participants. The aim of this study was to confirm these findings and to examine for the first time whether these VOCs are stable or change in concentration during the early treatment course. Moreover, it was investigated whether there is a correlation of the VOCs with the existing psychopathology of schizophrenia patients, i.e., whether the concentration of masses detected in the breath gas changes when the psychopathology of the participants changes. METHODS: The breath of a total of 22 patients with schizophrenia disorder was examined regarding the concentration of VOCs using proton transfer reaction mass spectrometry. The measurements were carried out at baseline and after two weeks at three different time points, the first time immediately after waking up in the morning, after 30 min, and then after 60 min. Furthermore, 22 healthy participants were investigated once as a control group. RESULTS: Using bootstrap mixed model analyses, significant concentration differences were found between schizophrenia patients and healthy control participants (m/z 19, 33, 42, 59, 60, 69, 74, 89, and 93). Moreover, concentration differences were detected between the sexes for masses m/z 42, 45, 57, 69, and 91. Mass m/z 67 and 95 showed significant temporal changes with decreasing concentration during awakening. Significant temporal change over two weeks of treatment could not be detected for any mass. Masses m/z 61, 71, 73, and 79 showed a significant relationship to the respective olanzapine equivalents. The length of hospital stay showed no significant relationship to the masses studied. CONCLUSION: Breath gas analysis is an easy-to-use method to detect differences in VOCs in the breath of schizophrenia patients with high temporal stability. m/z 60 corresponding to trimethylamine might be of potential interest because of its natural affinity to TAAR receptors, currently a novel therapeutic target under investigation. Overall, breath signatures seemed to stable over time in patients with schizophrenia. In the future, the development of a biomarker could potentially have an impact on the early detection of the disease, treatment, and, thus, patient outcome.

Consequences of the Lockdown: Domestic Violence During the COVID-19 Pandemic.

BACKGROUND: The global pandemic of the coronavirus disease 2019 (COVID-19) has presented many unique challenges to health systems. The hidden impact of COVID-19 and its associated lockdown have been an increased prevalence of domestic violence. OBJECTIVE: To increase our understanding of the connection between COVID-19 containment measures, domestic violence, and mental health in Germany, we conducted an online self-assessment survey of 98 domestic violence victims and 276 controls. All participants answered questions concerning domestic violence, emotional regulation skills, limitations due to and acceptance of containment measures, and quality of their contact experiences. RESULTS: There was no significant effect of "gender" x "domestic violence." Among victims of domestic violence, the number of women was considerably higher than the number of men. In addition, the factors "negative contact quality," "emotional regulation," and "resilience" differed significantly between the victims of domestic violence and the control group. CONCLUSIONS: The COVID-19 outbreak and associated containment and quarantine measures resulted in a "hidden pandemic" of domestic violence for which prevention programs and early victim assistance through the expansion of digital technologies are urgently needed. Prospective studies should expand empirical data to focus on the long-term psychological effects of domestic violence and biomarkers that can serve as warning signs of stress-related disorders.

Association of hospitalization with structural brain alterations in patients with affective disorders over nine years.

Repeated hospitalizations are a characteristic of severe disease courses in patients with affective disorders (PAD). To elucidate how a hospitalization during a nine-year follow-up in PAD affects brain structure, a longitudinal case-control study (mean [SD] follow-up period 8.98 [2.20] years) was conducted using structural neuroimaging. We investigated PAD (N = 38) and healthy controls (N = 37) at two sites (University of Münster, Germany, Trinity College Dublin, Ireland). PAD were divided into two groups based on the experience of in-patient psychiatric treatment during follow-up. Since the Dublin-patients were outpatients at baseline, the re-hospitalization analysis was limited to the Münster site (N = 52). Voxel-based morphometry was employed to examine hippocampus, insula, dorsolateral prefrontal cortex and whole-brain gray matter in two models: (1) group (patients/controls)×time (baseline/follow-up) interaction; (2) group (hospitalized patients/not-hospitalized patients/controls)×time interaction. Patients lost significantly more whole-brain gray matter volume of superior temporal gyrus and temporal pole compared to HC (pFWE = 0.008). Patients hospitalized during follow-up lost significantly more insular volume than healthy controls (pFWE = 0.025) and more volume in their hippocampus compared to not-hospitalized patients (pFWE = 0.023), while patients without re-hospitalization did not differ from controls. These effects of hospitalization remained stable in a smaller sample excluding patients with bipolar disorder. PAD show gray matter volume decline in temporo-limbic regions over nine years. A hospitalization during follow-up comes with intensified gray matter volume decline in the insula and hippocampus. Since hospitalizations are a correlate of severity, this finding corroborates and extends the hypothesis that a severe course of disease has detrimental long-term effects on temporo-limbic brain structure in PAD.

Longitudinal Gray Matter Development Associated With Psychotic Experiences in Young People.

Background: Gray matter abnormalities are observed across the psychosis spectrum. The trajectory of these abnormalities in healthy adolescents reporting subthreshold psychotic experiences (PEs) may provide insight into the neural mechanisms underlying psychotic symptoms. The risk of psychosis and additional psychopathology is even higher among these individuals who also report childhood adversity/DSM-5 diagnoses. Thus, the aims of this longitudinal study were to investigate PE-related volumetric changes in young people, noting any effects of childhood adversity/DSM-5 diagnosis. Methods: A total of 211 young people 11 to 13 years of age participated in the initial Adolescent Brain Development study. PE classification was determined by expert consensus at each time point. Participants underwent neuroimaging at 3 time points over 6 years. A total of 76 participants with at least one scan were included in the final sample; 34 who met criteria for PEs at least once across all the time points (PE group) and 42 control subjects. Data from 20 bilateral regions of interest were extracted for linear mixed-effects analyses. Results: Right hippocampal volume increased over time in the control group, with no increase in the PE group (p = .00352). DSM-5 diagnosis and childhood adversity were not significantly associated with right hippocampal volume. There was no significant effect of group or interaction in any other region. Conclusions: These findings further implicate right hippocampal volumetric abnormalities in the pathophysiology underlying PEs. Furthermore, as suggested by previous studies in those at clinical high risk for psychosis and those with first-episode psychosis, it is possible that these deficits may be a marker for later clinical outcomes.

Gut-brain axis volatile organic compounds derived from breath distinguish between schizophrenia and major depressive disorder.

BACKGROUND: Signatures from the metabolome and microbiome have already been introduced as candidates for diagnostic and treatment support. The aim of this study was to investigate the utility of volatile organic compounds (VOCs) from the breath for detection of schizophrenia and depression. METHODS: Patients with a diagnosis of major depressive disorder (MDD) or schizophrenia, as well as healthy controls, were recruited to participate. After being clinically assessed and receiving instruction, each participant independently collected breath samples for subsequent examination by proton transfer-reaction mass spectrometry. RESULTS: The sample consisted of 104 participants: 36 patients with MDD, 34 patients with schizophrenia and 34 healthy controls. Through mixed-model and deep learning analyses, 5 VOCs contained in the participants' breath samples were detected that significantly differentiated between diagnostic groups and healthy controls, namely VOCs with mass-to-charge ratios (m/z) 60, 69, 74, 88 and 90, which had classification accuracy of 76.8% to distinguish participants with MDD from healthy controls, 83.6% to distinguish participants with schizophrenia from healthy controls and 80.9% to distinguish participants with MDD from those with schizophrenia. No significant associations with medication, illness duration, age of onset or time in hospital were detected for these VOCs. LIMITATIONS: The sample size did not allow generalization, and confounders such as nutrition and medication need to be tested. CONCLUSION: This study established promising results for the use of human breath gas for detection of schizophrenia and MDD. Two VOCs, 1 with m/z 60 (identified as trimethylamine) and 1 with m/z 90 (identified as butyric acid) could then be further connected to the interworking of the microbiota-gut-brain axis.

Usability of the IDDEAS prototype in child and adolescent mental health services: A qualitative study for clinical decision support system development.

Introduction: Child and adolescent mental health services (CAMHS) clinical decision support system (CDSS) provides clinicians with real-time support as they assess and treat patients. CDSS can integrate diverse clinical data for identifying child and adolescent mental health needs earlier and more comprehensively. Individualized Digital Decision Assist System (IDDEAS) has the potential to improve quality of care with enhanced efficiency and effectiveness. Methods: We examined IDDEAS usability and functionality in a prototype for attention deficit hyperactivity disorder (ADHD), using a user-centered design process and qualitative methods with child and adolescent psychiatrists and clinical psychologists. Participants were recruited from Norwegian CAMHS and were randomly assigned patient case vignettes for clinical evaluation, with and without IDDEAS. Semi-structured interviews were conducted as one part of testing the usability of the prototype following a five-question interview guide. All interviews were recorded, transcribed, and analyzed following qualitative content analysis. Results: Participants were the first 20 individuals from the larger IDDEAS prototype usability study. Seven participants explicitly stated a need for integration with the patient electronic health record system. Three participants commended the step-by-step guidance as potentially helpful for novice clinicians. One participant did not like the aesthetics of the IDDEAS at this stage. All participants were pleased about the display of the patient information along with guidelines and suggested that wider guideline coverage will make IDDEAS much more useful. Overall, participants emphasized the importance of maintaining the clinician as the decision-maker in the clinical process, and the overall potential utility of IDDEAS within Norwegian CAMHS. Conclusion: Child and adolescent mental health services psychiatrists and psychologists expressed strong support for the IDDEAS clinical decision support system if better integrated in daily workflow. Further usability assessments and identification of additional IDDEAS requirements are necessary. A fully functioning, integrated version of IDDEAS has the potential to be an important support for clinicians in the early identification of risks for youth mental disorders and contribute to improved assessment and treatment of children and adolescents.

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies.

The promise of machine learning has fueled the hope for developing diagnostic tools for psychiatry. Initial studies showed high accuracy for the identification of major depressive disorder (MDD) with resting-state connectivity, but progress has been hampered by the absence of large datasets. Here we used regular machine learning and advanced deep learning algorithms to differentiate patients with MDD from healthy controls and identify neurophysiological signatures of depression in two of the largest resting-state datasets for MDD. We obtained resting-state functional magnetic resonance imaging data from the REST-meta-MDD (N = 2338) and PsyMRI (N = 1039) consortia. Classification of functional connectivity matrices was done using support vector machines (SVM) and graph convolutional neural networks (GCN), and performance was evaluated using 5-fold cross-validation. Features were visualized using GCN-Explainer, an ablation study and univariate t-testing. The results showed a mean classification accuracy of 61% for MDD versus controls. Mean accuracy for classifying (non-)medicated subgroups was 62%. Sex classification accuracy was substantially better across datasets (73-81%). Visualization of the results showed that classifications were driven by stronger thalamic connections in both datasets, while nearly all other connections were weaker with small univariate effect sizes. These results suggest that whole brain resting-state connectivity is a reliable though poor biomarker for MDD, presumably due to disease heterogeneity as further supported by the higher accuracy for sex classification using the same methods. Deep learning revealed thalamic hyperconnectivity as a prominent neurophysiological signature of depression in both multicenter studies, which may guide the development of biomarkers in future studies.